CN116056862A

CN116056862A - Computer-implemented method for controlling and/or monitoring at least one injection molding process

Info

Publication number: CN116056862A
Application number: CN202180055695.1A
Authority: CN
Inventors: A·沃尔尼; R·詹科比; A·翁尼诗; O·盖革
Original assignee: BASF SE
Current assignee: BASF SE
Priority date: 2020-08-14
Filing date: 2021-08-13
Publication date: 2023-05-02
Also published as: US20230347564A1; WO2022034210A1; KR20230051258A; EP4196333A1; JP2023538885A; BR112023002471A2

Abstract

A computer-implemented method for controlling and/or monitoring at least one injection molding process in at least one injection molding machine (110) is presented. The injection molding process is based on a number of process parameters. The method comprises the following steps: a) Providing, by at least one external processing unit (118), a set of input parameters, wherein the set of input parameters includes at least one simulation model, material specific parameters, and injection molding machine parameters; b) An external processing unit (118) for simulating the injection molding process based on the set of input parameters, determining at least one predicted process parameter of the simulated injection molding process by applying an optimization algorithm of at least one optimization objective aspect on the simulation model, wherein the predicted process parameter is provided to the injection molding machine via at least one interface; c) Performing at least one injection molding process using the injection molding machine (110) to generate at least one workpiece (114) based on the predicted process parameters, determining at least one property of the generated workpiece (114), comparing the property with an optimization target, wherein in case the property of the generated workpiece (114) deviates from the optimization target, adapting at least one process parameter of the injection molding machine (110) according to the comparison, repeating the injection molding process with the adapted process parameters, determining the property of the generated workpiece (114), and comparing the property with the optimization target until the property of the generated workpiece (114) coincides with the optimization target at least within a predetermined tolerance; d) At least one actual process parameter of the injection molding process is determined, the actual process parameter and the predicted process parameter are compared, and a simulation model is adapted based on the comparison.

Description

Computer-implemented method for controlling and/or monitoring at least one injection molding process

Technical Field

The present invention relates to a computer implemented method, a computer program, a computer readable storage medium and an automatic control system for controlling and/or monitoring at least one injection molding process. Generally, such methods, systems and apparatus may be used for technical design or configuration purposes, for example, during development or production stages of an injection molding process. However, further applications are also possible.

Background

Injection molding processes are the most recent common manufacturing processes for small and large scale manufacturing industries. In a typical injection molding process, a plastic material (such as a thermoplastic, thermoset, or elastomeric material) is generally melted during heating and then injected into an empty mold, for example, under applied pressure. The plastic material is then typically hardened during cooling or solidification to maintain the form given by the mold, thereby becoming an article of manufacture. It allows for a large replication of the product formed by the mold. Because of the high cost of designing and configuring the mold, if any problem occurs during injection molding, it is not easy to modify the mold. Therefore, to minimize production costs and waste, the filling process of the mold or cavity has been simulated previously, typically using common simulation methods.

Today, injection molding simulations (e.g., from Moldflow) can be used to optimize the tooling and filling process for a given part. Moldflow has two core products: moldflow advser, which provides manufacturability guidance and directional feedback for standard part and mold designs; and Moldflow weight, which provides the final results for flow, cooling and warpage, and supports a specialized molding process, see en.

It is known that optimization procedures can be carried out in the injection molding machine itself, for example from DE 102013 111 257B3, DE 10 2018 107 233 A1 or EP3294519B1.

While recent injection molding process optimization and simulation methods have advantages, there are still some technical challenges. Thus, simulating and optimizing the injection molding process may still be very time consuming and complex, the required computational power may still be very high, which may not be possible in the injection molding machine itself, as the injection molding machine has to produce a work piece without simulation results. Furthermore, it would be desirable to be able to improve the known simulation and optimization methods for injection molding in terms of efficiency and accuracy of the simulation and optimization process.

In other technical fields (such as for chemical processes) further optimization methods are known, as described in WO 2019/138118, WO 2019/138120, WO 2019/138122.

US 5,900,259A describes a molding condition optimizing system for an injection molding machine, which system comprises a plastic flow condition optimizing section and an operating condition determining section. The plastic flow condition optimizing section performs plastic flow analysis on the molded part model, and determines an optimum flow condition of an injection molding process of the injection molding machine in a filling stage and a packaging stage by repeatedly performing automatic calculation using a result of the plastic flow analysis and the plastic flow analysis itself. The operation condition determining section includes: an injection side condition determining section for determining an optimum injection side condition of the injection molding machine based on the optimum flow condition obtained by the plastic flow condition optimizing means and a knowledge database concerning the injection condition; and a mold-closing-side condition determining section for determining an optimum mold-closing-side condition based on the molded part shape data, the plastic flow analysis result, the mold design data, and the knowledge database concerning the mold-closing conditions generated by the plastic flow condition optimizing means.

US 2018/181694 A1 describes a method of optimizing a process optimization system for a molding machine, the method comprising setting, by a user, setting data on an actual molding machine, obtaining a first value of at least one descriptive variable of the molding process based on the set data set and/or on a cyclically performed molding process, and obtaining a second value of the at least one descriptive variable based on data from the process optimization system. According to a predetermined distinguishing criterion, it is checked whether the first value and the second value are different from each other. If the inspection reveals that the first value and the second value are different from each other, the process optimization system is modified such that the first value of the descriptive variable substantially replaces the second value of the descriptive variable when applied to the molding machine and/or the molding process.

WO 2019/106499 A1 describes a method for processing molding parameters of an injection molding machine obtained by CAE. CAE simulation generates a simulation result, the first machine parameter being generated by electronically processing the simulation result, the second machine parameter being obtained from execution of another molding process of the same object, different from the first machine parameter; in an electronic database accessible to a user, the first and second machine parameters are stored in association in a common collection. In a further variant, the last method step is replaced by processing the first and second machine parameters with software and modifying the machine parameters calculated with a subsequent CAE simulation as a function of the processing produced by said software.

US 2006/224540 A1 describes test molding and mass production molding, which are performed by an injection molding machine comprising a control device, in which a neural network is used. The quality prediction function determined based on the test molding is modified as needed during mass production molding.

EP 0 368 300 A2 describes an optimal molding condition setting system for an injection molding machine. The system includes a molten material flow analysis means for analyzing the resin flow, the resin cooling and the structure/strength of the molded product by using a designed model mold, and also includes an analysis result evaluation means for determining an initial molding condition and an allowable range thereof based on the analysis result. Initial molding conditions are set into the injection molding machine, and test injection is performed in order to check the molded product for defects. If a defect of the molded product is found, defect data is input into a molded defect eliminating device.

Problems to be solved

It is therefore desirable to provide devices and methods that address the above-mentioned technical challenges. In particular, methods, systems, programs and databases should be presented to further enhance the performance of simulation and optimization of injection molding processes, particularly in terms of efficiency and accuracy, as compared to devices, methods and systems known in the art.

Disclosure of Invention

This problem is solved by a method, system, program and database having the features of the independent claims. Advantageous embodiments which can be realized in isolation or in any arbitrary combination are listed in the dependent claims.

As used hereinafter, the terms "having," "including," or "containing," or any arbitrary grammatical variants thereof, are used in a non-exclusive manner. Thus, these terms may refer to either the absence of a further feature in the entity described in this context or the presence of one or more further features in addition to the features introduced by these terms. As an example, the expressions "a has B", "a includes B" and "a contains B" may refer to both the case where no other element is present in a except B (i.e. a consists only and exclusively of B) and the case where one or more further elements are present in entity a except B, such as elements C, C and D or even more.

Furthermore, it should be noted that when the terms "at least one," "one or more," or similar expressions (meaning that the feature or element is likely to be present one or more times) introduce a corresponding feature or element, these expressions will typically be used only once. In the following, the expression "at least one" or "one or more" will in most cases not be repeated when referring to the corresponding feature or element, despite the fact that the corresponding feature or element may be present one or more times.

Furthermore, as used hereinafter, the terms "preferably," "more preferably," "particularly," "more particularly," "specifically," "more particularly," or similar terms are used in conjunction with optional features, but do not limit the substitution possibilities. Thus, the features introduced by these terms are optional features and are not intended to limit the scope of the claims in any way. As the skilled person will appreciate, the invention may be implemented using alternative features. Also, features introduced by the expression "in one embodiment of the invention" or similar are intended as optional features, without any limitation to alternative embodiments of the invention, without any limitation to the scope of the invention, and without any limitation to the possibility of combining features introduced in this way with other optional or non-optional features of the invention.

In a first aspect of the invention, a computer-implemented method for controlling and/or monitoring at least one injection molding process in at least one injection molding machine is disclosed.

As used herein, the term "computer-implemented" is a broad term and is given its ordinary and customary meaning to those skilled in the art, and is not limited to a specific or customized meaning. The term may particularly refer to, but is not limited to, a process implemented in whole or in part by using a data processing device, such as a data processing device comprising at least one processor. Thus, the term "computer" may generally refer to a device or combination of devices or a network of devices having at least one data processing apparatus (such as at least one processor). In addition, the computer may also include one or more further components, such as at least one of a data storage device, an electronic interface, or a human-machine interface. As used herein, the term "processor" or "processing unit" is a broad term and is given its ordinary and customary meaning to those skilled in the art and is not limited to a specific or customized meaning. The term may particularly refer to, but is not limited to, any logic circuitry configured to perform the basic operations of a computer or system, and/or, in general, devices configured to perform computing or logic operations. In particular, the processor may be configured to process basic instructions that drive a computer or system. As one embodiment, a processor may include at least one Arithmetic Logic Unit (ALU), at least one Floating Point Unit (FPU), such as a math coprocessor or a digital coprocessor, a plurality of registers, particularly registers configured to provide operands to the ALU and store results of operations, and memory, such as L1 and L2 cache memory. In particular, the processor may be a multi-core processor. In particular, the processor may be or may include a Central Processing Unit (CPU). Additionally or alternatively, the processor may be or may include a microprocessor, so that in particular, the elements of the processor may be contained in a single Integrated Circuit (IC) chip. Additionally or alternatively, the processor may be or include one or more Application Specific Integrated Circuits (ASICs) and/or one or more Field Programmable Gate Arrays (FPGAs) or the like.

As used herein, the term "molding process" is a broad term and is given its ordinary and customary meaning to those skilled in the art and is not limited to a specific or customized meaning. The term may particularly refer to, but is not limited to, a process or procedure for shaping at least one material into any form or shape. As used herein, the term "injection molding process" is a broad term and is given its ordinary and customary meaning to those of ordinary skill in the art and is not limited to a specific or customized meaning. The term may particularly refer to, but is not limited to, the type of molding process that is performed by injecting molten material into a mold.

As used herein, the term "mold" is a broad term and is given its ordinary and customary meaning to those skilled in the art and is not limited to a specific or customized meaning. The term may particularly refer to, but is not limited to, a mold or a molding, for example, a molding giving a mold or a frame. In particular, as used herein, a mold may refer to any mold and/or molding that includes at least one cavity, such as at least one molding that gives a structure and/or cut. The mold may be particularly useful in an injection molding process wherein at least one block of molten material may be injected into at least one cavity of the mold. For simplicity, the terms "mold" and "mold cavity" may be used interchangeably herein. As one example, a mold having at least one cavity may be used in a molding process for forming a material. In particular, a molten mass of material injected into a mold cavity may be imparted to the negative form and/or geometry of the cavity. In particular, the mold may be used to manufacture at least one workpiece, also referred to as a part, wherein the manufactured workpiece may have a negative form and/or shape of the mold cavity.

The molding process may be configured to manufacture at least one workpiece. As used herein, the term "workpiece" is a broad term and is given its ordinary and customary meaning to those skilled in the art and is not limited to a specific or customized meaning. The term may particularly refer to, but is not limited to, any part or element. In particular, the workpiece may be or may comprise a component of any machine or apparatus. For example, the workpiece may have, at least in part, a negative shape (negative shape) of a mold or mold cavity in a molding process used to manufacture the part. Thus, the injection molding process may be or may refer to a shape imparting procedure for manufacturing a workpiece.

As used herein, the term "injection molding machine" is a broad term and is given its ordinary and customary meaning to those skilled in the art, and is not limited to a specific or customized meaning. The term may particularly refer to, but is not limited to, any device or machine configured to perform an injection molding process. The injection molding machine may include at least one injection unit and at least one mold locking unit.

The injection molding process is based on a number of process parameters. As used herein, the term "process parameter" is a broad term and is given its ordinary and customary meaning to those skilled in the art and is not limited to a specific or customized meaning. The term may particularly refer to, but is not limited to, at least one settable and/or selectable and/or adjustable and/or configurable parameter affecting the injection molding process. The process parameters may relate to the operating conditions of the injection molding machine. In particular, the process parameters may be injection molding machine parameters. For example, the process parameters may include one or more of polymer melt temperature, barrel temperature, injection unit temperature, screw speed, injection speed, holding pressure, holding time, cooling or solidification time, at least one cooling or solidification parameter (such as yield of cooling or solidification medium, or cooling or solidification medium temperature). The injection molding machine parameters may further include the dimensions of the machine, such as mold clamping force, draw bar clearance, injection unit, the dimensions of the equipment of the machine, such as barrel diameter or maximum barrel temperature, etc.

As used herein, the term "control" is a broad term and is given its ordinary and customary meaning to those skilled in the art and is not limited to a specific or customized meaning. The term may particularly refer to, but is not limited to, determining and/or adjusting at least one process parameter. As used herein, the term "monitoring" is a broad term and is given its ordinary and customary meaning to those of ordinary skill in the art and should not be limited to a specific or customized meaning. The term may particularly refer to, but is not limited to, quantitative and/or qualitative determination of at least one process parameter.

The computer-implemented method comprises the following steps, which may be performed in a given order. However, a different order is also possible. Furthermore, one or more or even all of the steps may be performed once or repeatedly. Furthermore, the method steps may be performed in a timely overlapping manner or even in parallel. The method may further comprise additional method steps not listed.

The method comprises the following steps:

a) Providing, by at least one external processing unit, a set of input parameters, wherein the set of input parameters includes at least one simulation model, material specific parameters, and injection molding machine parameters;

b) An external processing unit simulating the injection molding process based on the set of input parameters and determining at least one predicted process parameter of the simulated injection molding process by applying an optimization algorithm on at least one optimization objective aspect on a simulation model, wherein the predicted process parameter is provided to the injection molding machine via at least one interface;

c) Performing at least one injection molding process using an injection molding machine based on the predicted process parameters to generate at least one workpiece, determining at least one attribute of the generated workpiece, and comparing the attribute to an optimization target, wherein in the event that the attribute of the generated workpiece deviates from the optimization target, adapting the at least one process parameter of the injection molding machine according to the comparison, repeating the injection molding process with the adapted process parameters, determining the attribute of the generated workpiece, and comparing the attribute to the optimization target until the attribute of the generated workpiece coincides with the optimization target at least within a predetermined tolerance;

d) At least one actual process parameter of the injection molding process is determined, the actual process parameter and the predicted process parameter are compared, and a simulation model is adapted based on the comparison.

As used herein, the term "external processing unit" is a broad term and is given its ordinary and customary meaning to those of ordinary skill in the art and is not limited to a specific or customized meaning. The term may particularly refer to, but is not limited to, at least one processing unit designed separately from the injection molding machine. The injection molding machine may comprise an internal processing unit, in particular configured for controlling and monitoring machine parameters. The external processing unit may be configured to transmit data to and/or receive data from the internal processing unit via the at least one communication interface. The internal processing unit may be configured to transmit data to and/or receive data from the external processing unit via the at least one communication interface. The external processing unit may include a plurality of processors. The external processing unit may be and/or include a cloud computing system.

The external processing unit may comprise at least one database. As used herein, the term "database" is a broad term and is given its ordinary and customary meaning to those of ordinary skill in the art and is not limited to a specific or customized meaning. The term may particularly refer to, but is not limited to, any collection of information. The database may be stored in at least one data storage device. In particular, the database may contain any collection of information. The data storage device may be or may include at least one element selected from the group consisting of: at least one server, at least one server system comprising a plurality of servers, at least one cloud server, or a cloud computing infrastructure.

As used herein, the term "communication interface" is a broad term and is given its ordinary and customary meaning to those skilled in the art and is not limited to a specific or customized meaning. The term may particularly refer to, but is not limited to, an item or element forming a boundary configured for transmitting information. In particular, the communication interface may be configured for transmitting information from a computing device (e.g., a computer), such as sending or outputting the information, for example, onto another device. Additionally or alternatively, the communication interface may be configured to transmit information to a computing device, such as to a computer, for example, to receive information. The communication interface may particularly provide means for transmitting or exchanging information. In particular, the communication interface may provide a data transfer connection, e.g. bluetooth, NFC, inductive coupling, etc. As one example, the communication interface may be or include at least one port including one or more network or internet ports, USB ports, and disk drives. The communication interface may be at least one network interface.

As used herein, the term "providing" is a broad term and is given its ordinary and customary meaning to those skilled in the art and is not limited to a specific or customized meaning. The term may particularly refer to, but is not limited to, retrieving and/or selecting an input parameter set. As used herein, the term "retrieve" is a broad term and is given its ordinary and customary meaning to those of ordinary skill in the art and is not limited to a specific or customized meaning. The term may particularly refer to, but is not limited to, the process by which a system (particularly a computer system) generates and/or obtains data from any data source, such as from a data store, from a network, or from a further computer or computer system. In particular, the retrieval may be via at least one computer interface (such as via a port, such as a serial or parallel port). The retrieval may comprise several sub-steps, such as a sub-step of obtaining one or more primary information items and generating secondary information by utilizing the primary information, such as by applying one or more algorithms to the primary information, e.g. by using a processor.

As used herein, the term "input parameter set" is a broad term and is given its ordinary and customary meaning to those of ordinary skill in the art and is not limited to a specific or customized meaning. The term may particularly refer to, but is not limited to, information about simulation models, material specific parameters and injection molding machine parameters.

As used herein, the term "injection molding machine parameters" is a broad term and is given its ordinary and customary meaning to those of ordinary skill in the art and is not limited to a specific or customized meaning. The term may particularly refer to, but is not limited to, parameters affecting the operating conditions of the injection molding machine. The injection molding machine parameters may include settings of machine components of the injection molding machine. The injection molding machine parameters may include specific values and/or parameter curves. The injection molding machine parameters may include at least one parameter selected from the group consisting of: polymer melt temperature, barrel temperature, injection unit temperature, screw speed, injection speed, holding pressure, holding time, cooling or solidification parameters (such as yield of cooling or solidification medium, cooling or solidification medium temperature).

As used herein, the term "material specific parameter" is a broad term and is given its ordinary and customary meaning to those of ordinary skill in the art and is not limited to a specific or customized meaning. The term may particularly refer to, but is not limited to, information about the material or materials used in the injection molding process. The material specific parameters may be provided by a material provider and/or may be downloaded from a website or other database. The material provider may have a number of product specific data such as rheology data, viscosity, and lot specific data for each material produced. The material specific parameters comprise at least one parameter selected from the group consisting of: compressibility, flow characteristics, temperature characteristics.

The material (in particular, the material used in the moulding process, for example, for manufacturing the workpiece) may for example be or may comprise a plastics material. As used herein, the term "plastic material" is a broad term and is given its ordinary and customary meaning to those skilled in the art, and is not limited to a specific or customized meaning. The term may particularly refer to, but is not limited to, any thermoplastic, thermoset or elastomeric material. In particular, the plastic material may be a mixture of substances consisting of monomers and/or polymers. In particular, the plastic material may be or may comprise a thermoplastic material. Additionally or alternatively, the plastic material may be or include a thermoset material. Additionally or alternatively, the plastic material may comprise an elastic material. During the manufacture of the workpiece, the material may in particular be in a molten state.

As used herein, the term "simulate" or "simulate" is a broad term and is given its ordinary and customary meaning to those skilled in the art, and is not limited to a specific or customized meaning. The term may particularly refer to, but is not limited to, a process for particularly approximating a real injection molding process. As used herein, the term "simulation model" is a broad term and is given its ordinary and customary meaning to those of ordinary skill in the art and is not limited to a specific or customized meaning. The term may particularly refer to, but is not limited to, at least one model based on which a simulation is performed. The simulation model may be generated by software on an external processing unit or the simulation model may be a dataset in the software.

The simulation model may include at least one trained and trainable model. As used herein, the term "trained model" is a broad term and is given its ordinary and customary meaning to those of ordinary skill in the art and is not limited to a specific or customized meaning. The term may particularly refer to, but is not limited to, a mathematical model trained on at least one training data set. As used herein, the term "trainable model" is a broad term and is given its ordinary and customary meaning to those of ordinary skill in the art and is not limited to a specific or customized meaning. The term may particularly refer to, but is not limited to, the fact that the simulation model may be further trained and/or updated based on additional training data. In particular, the simulation model is trained on a training data set. The simulation model may be trained using machine learning. The simulation model may be at least partially data driven by training on data of historical production runs. As used herein, the term "data-driven" is a broad term and is given its ordinary and customary meaning to those skilled in the art, and is not limited to a specific or customized meaning. The term may refer specifically, but is not limited to, the fact that the model is an empirical, predictive model. Specifically, the data-driven model is derived from analysis of experimental data from a previous injection molding process. The term "historical production run" refers to an injection molding process at a past or earlier point in time. In particular, for further training of the simulation model, a training data set may be generated from the comparison data of the actual and predicted process parameters determined in step d). As used herein, the term "at least partially data-driven model" is a broad term and is given its ordinary and customary meaning to those of ordinary skill in the art and is not limited to a specific or customized meaning. The term may particularly refer to, but is not limited to, the fact that the trained model comprises a data-driven model part, wherein the model may comprise further or other model parts. As used herein, the term "machine learning" is a broad term and is given its ordinary and customary meaning to those of ordinary skill in the art and is not limited to a specific or customized meaning. The term may particularly refer to, but is not limited to, a method of automatically modeling a machine learning model (particularly a predictive model) using Artificial Intelligence (AI). The external processing unit may be configured to perform and/or execute at least one machine learning algorithm. The simulation model may be based on the results of at least one machine learning algorithm. The machine learning algorithm may include decision trees, naive bayes classification, nearest neighbor, neural network, convolutional neural network, generating an countermeasure network, support vector machine, linear regression, logistic regression, random forest, and/or gradient boosting algorithm. Preferably, the machine learning algorithm is organized to process inputs with high dimensions into outputs of much lower dimensions. This machine learning algorithm is referred to as "intelligent" because it can be "trained". The algorithm may be trained using training data records. The training data record may include training input data and corresponding training output data. The training output data of the training data record may be the result that the machine learning algorithm expects to produce when given training input data of the same training data record as input. Deviations between this expected result and the actual result produced by the algorithm can be observed and assessed by a "loss function". This loss function may be used as feedback to adjust parameters of the internal processing chain of the machine learning algorithm. For example, the parameters may be adjusted with an optimization objective that minimizes the value of the loss function that would result when all training input data is fed into the machine learning algorithm and the results are compared to the corresponding training output data. The result of this training may be that given relatively few training data records as "ground truth," the machine learning algorithm is able to perform its work well on many orders of magnitude higher input data records. Thus, the simulation model may include at least one algorithm and model parameters. The simulation model parameters may be generated using at least one artificial neural network. The simulation model, in particular the model parameters, can be adapted in step d) so that further training is possible.

The simulation model may include digital twinning of the injection molding process. The simulation model is configured for simulating an injection molding process. The simulation model may include a fill simulation. In particular, the simulation model may be configured to simulate filling a mold cavity with at least one molten mass of material. The simulation model may be configured to simulate the manufacture of the workpiece. The simulation model may be configured to simulate the geometry and/or shape of the workpiece. The simulation model may include an intensity analysis.

The simulation model may use geometric data of the workpiece to be manufactured. As used herein, the term "geometric data" is a broad term and is given its ordinary and customary meaning to those of ordinary skill in the art and is not limited to a specific or customized meaning. The term may particularly refer to, but is not limited to, information in the three-dimensional form or shape of any object or element. In particular, geometric data (such as information of a three-dimensional shape) may exist in computer-readable form, such as a computer-compatible dataset, in particular a digital dataset. As an example, the geometric data may be or may include computer aided design data (CAD data). In particular, the three-dimensional geometric data may be or may include CAD data describing the form or shape of the object or element.

The simulation model may be configured to consider material specific properties. The simulation model may include digital twinning of the material. The simulation model may be configured to consider batch properties of a raw material batch, such as viscosity of the material batch. The simulation process is not performed on the injection molding machine itself, but by an external processing unit, such as by at least one cloud computing system. This may allow for influencing additional parameters of the injection molding process in addition to the machine parameters and/or sensor parameters provided by and/or available in the injection molding machine and/or at least one sensor thereof. These additional parameters may relate to external knowledge, for example knowledge of the material provider, such as specific data of the product, such as rheological data, viscosity and/or algorithms, and/or specific data of the production material.

It is possible to use simulation data, process data and product related data in process optimization of a cloud-based injection molding process. As mentioned above, the material provider may have a number of product specific data, such as rheological data, viscosity, and lot specific data for each material produced. The present invention proposes to establish a closed loop between the simulation and the injection molding process so that the simulation parameters can be used directly in the injection molding process. Furthermore, conversely, the process data can be used to optimize the modeling process using a machine learning model. By using cloud-based materials and digital twinning of the injection molding process, lot specific information of the materials can be further correlated to the simulated manufacturing process, thereby enabling the efficiency of the injection molding process to be further improved.

As used herein, the term "simulated predicted process parameters of an injection molding process" is a broad term and is given its ordinary and customary meaning to those of ordinary skill in the art and is not limited to a specific or customized meaning. The term may particularly refer to, but is not limited to, expected values of process parameters, in particular for achieving an optimal manufacturing result and/or optimal use of resources. The predicted process parameter may be a parameter that affects the injection molding process. The predicted process parameters may be determined for optimizing the injection molding process. In known systems and devices, such as described in US 5 900 259A, optimization is performed in view of the optimization of the workpiece. In contrast, the present invention refers to process optimization. Process optimization may also take into account optimal use of resources in addition to optimal manufacturing results.

Step b) may comprise at least one optimization step. As used herein, the term "optimized" is a broad term and is given its ordinary and customary meaning to those skilled in the art, and is not limited to a specific or customized meaning. The term may particularly refer to, but is not limited to, a process of selecting an optimal parameter set in relation to an optimization objective from a parameter space of possible parameters. As used herein, the term "optimization objective" is a broad term and is given its ordinary and customary meaning to those of ordinary skill in the art and is not limited to a specific or customized meaning. The term may particularly refer to, but is not limited to, at least one criterion under which optimization is performed. The optimization objective may include at least one optimization objective and accuracy and/or precision. The optimization objective may be at least one attribute of the workpiece. The property of the workpiece may be at least one element selected from the group consisting of: the weight of the workpiece, the size of the workpiece, and the degree of warping. The optimization objective may be pre-specified, such as by at least one customer and/or a user of at least one injection molding machine. The optimization objective may be a specification of at least one user. The user may choose to optimize the objective and the desired accuracy and/or precision. The predicted process parameters are provided to the injection molding machine via at least one interface, in particular via a communication interface. In known systems and devices, such as described in US 5 900 299 a, parameters defining the injection molding process are stored in an injection molding machine. Thus, typically, these parameters are static. In contrast, the present invention proposes a self-learning method and in particular continuously improves the performance of an injection molding process by adapting a simulation model in step d) taking into account the newly determined predicted process parameters in step c) and using the improved simulation model in step c) to predict improved process parameters for performing at least one injection molding process. Thus, by performing steps a) to d) a loop or circuit is proposed.

The method includes performing at least one injection molding process using an injection molding machine based on predicted process parameters for generating at least one workpiece. The use of predicted process parameters to perform an injection molding process not only refers to relying on machine parameters and/or sensor parameters provided by and/or available in the injection molding machine and/or at least one sensor thereof, but also takes into account external knowledge, e.g., knowledge of the material supplier (such as product specific data, e.g., rheology data, viscosity and/or algorithms) and/or specific data of the production material. The injection molding process may be continually improved using predicted process parameters. The manufactured workpiece may be measured, for example, by using optical or tactile measurement techniques, such as scanning. As used herein, the term "scan" is a broad term and is given its ordinary and customary meaning to those of ordinary skill in the art and is not limited to a specific or customized meaning. The term may particularly refer to, but is not limited to, any process or procedure for inspecting any object or data. The scanning may include determining the shape and size of the workpiece. The scanning may be performed specifically automatically. The scanning may be performed autonomously by the computer or by a network of computers.

The determined properties of the workpiece may be compared to an optimization objective. The comparison may include determining a deviation from a target shape and/or target size (also denoted as target size). If the difference between the determined attribute and the optimization target is above the tolerance limit, the generated workpiece is considered to deviate from the target shape and/or target size. The tolerance limit may depend on such things as the accuracy of the determination of the attributes and/or the customer requirements.

If the generated properties of the workpiece deviate from the optimization targets, at least one process parameter of the injection molding machine is adapted based on the comparison.

For example, comparing the determined properties of the workpiece with the optimization objectives may reveal that the workpiece deviates from the desired shape, particularly with respect to twisting, warping, wavy surfaces and angular deviations. This may be due to the difference in shrinkage tendency (shrinkage potential) of the respective regions of the workpiece. The difference in shrinkage may be due to the difference in degree of accumulation in different regions of the workpiece, as well as the difference in orientation of the fibers and polymer chains. A further reason may be that the selected mould temperature is disadvantageous, that the moulded work piece has a different wall thickness, that the pressure gradient of the work piece along the flow path is too high, that the selected cooling time is so short that the work piece is deformed after removal from the mould at too high a temperature, that a disadvantageous material is used, or that the glass fibres of the glass fibre reinforced thermoplastic are mainly oriented in the flow direction. In the latter case, deviations may occur if the orientation of the glass fibers varies at different places. This is due to, for example, an offset in the flow, an orientation effect at the flow path ends, weld lines and gates. Based on the comparison, at least one of the following process parameters of the injection molding machine can be adjusted: changing the temperature of the mold halves and sliding cores, increasing the cooling time, adapting the process so that the molding is not held by stitching or by negative drawing, changing the holding pressure, and changing the holding time. Furthermore, the materials used may be changed in consideration of the comparison. In particular materials with low warp curvature, such as mixtures with amorphous phases, can be used. In addition, the workpiece design may also be changed. The process parameters of the injection molding machine may be adapted with respect to a predetermined hierarchy. For example, the mold temperature may be adapted first, and then the cooling time may be adapted. Subsequently, further process parameters may be adapted.

For example, comparing the determined attribute of the workpiece with the optimization objective may reveal that the workpiece includes at least one indentation mark. As used herein, the term "recessed mark" is a broad term and is given its ordinary and customary meaning to those skilled in the art, and is not limited to a specific or customized meaning. The term may particularly refer to, but is not limited to, indentations in the surface of the molded workpiece. The dishing marks may occur mainly where the wall cross-section increases. This may result in a local increase in volume shrinkage, thereby pulling the surface layer inwards. Sometimes, the depressed marks occur after ejection from the mold when the hot center of the polymer heats the already cooled edge layers, causing them to yield. Sometimes they can only be identified by the difference in gloss compared to the surrounding area. The dishing signature may occur for a number of reasons, for example, if the volume shrinkage during the cooling stage is not sufficiently compensated by the holding pressure, or the design of the workpiece is not suitable for processing such plastics (e.g., increased wall thickness of the material portion, abrupt changes in wall thickness along the flow path), or there is no melt buffering, or a large pressure loss occurs in the machine nozzle and/or gate system, or the workpiece is cast as a thin wall. Based on the comparison, at least one of the following process parameters of the injection molding machine may be adapted: increasing holding pressure, increasing holding time, lowering melt temperature, lowering mold temperature, changing pressure delivery per flow path by changing wall thickness of the molded workpiece, extending metering stroke and adjusting transition points as needed, adapting sealing function of check valve, adapting barrel wear and expanding flow path and gate system flow cross section, adapting workpiece position (such as in the area of greatest wall thickness). In addition, the design of the workpiece may also be changed. The process parameters of the injection molding machine may be adapted with respect to a predetermined hierarchy. For example, the holding pressure can be adapted first, then the holding time, then the melt temperature, then further process parameters.

The injection molding process is repeated with the adapted process parameters, the properties of the generated work piece are determined and compared with the optimization target until the properties of the generated work piece agree with the optimization target at least within a predetermined tolerance.

Step d) includes determining at least one actual process parameter of the injection molding process. The injection molding machine may be configured to measure and/or monitor at least one process parameter of the process during the injection molding process. The at least one actual process parameter may be at least one process parameter that is measurable and/or monitorable during the injection molding process, for example by using at least one sensor. The term "during the injection molding process" may refer to a time span between the beginning and the end of the injection molding process and/or a time span in which the process conditions are expected to be substantially comparable to the process conditions in the injection molding process. The injection molding machine may be configured to measure process parameters in real time and adapt the process parameters during operation. The injection molding machine may be configured to measure at least one actual process parameter in real time. The injection molding machine may be configured to adapt at least one actual process parameter in operation. In case step c) comprises determining a plurality of predicted process parameters, then step d) may comprise determining a plurality of process parameters, such as a set of process parameters defining an injection molding process. The injection molding machine may include at least one sensor. The measured parameters of the injection molding machine may be registered and transmitted to an external processing unit. The injection molding machine may include at least one element selected from the group consisting of: a temperature sensor; a pressure sensor; and (3) a clock. For example, the at least one actual process parameter may be at least one parameter selected from the group consisting of: polymer melt temperature, barrel temperature, injection unit temperature, screw speed, injection speed, holding pressure, holding time, cooling or solidification time, at least one cooling or solidification parameter (e.g., yield of cooling or solidification medium, or cooling or solidification medium temperature). Step d) may comprise determining an actual set of process parameters to be optimized, in particular actual process parameters corresponding to the predicted process parameters in step c). Thus, not only a single process parameter but also a plurality of process parameters, in particular a set of process parameters defining an injection molding process, may be used in the optimization cycle.

Step d) further comprises comparing the actual process parameters with the predicted process parameters and adapting the simulation model based on the comparison. In case a plurality of predicted process parameters are determined in step c), step d) may further comprise comparing the corresponding actual process parameters with the corresponding predicted process parameters and adapting the simulation model based on the comparison. The comparison may include determining a deviation of the predicted process parameter from the actual process parameter, or vice versa. If the difference is above the tolerance limit, the actual process parameter is deemed to deviate from the predicted process parameter. The tolerance limit may depend on the measurement accuracy. The comparison may be performed by an internal processing unit of the injection molding machine. Information about the deviations and/or the actual process parameters may be transmitted to an external processing unit. The external processing unit may be configured to adjust the simulation model, in particular the model parameters, based on information about the deviations and/or the actual process parameters.

The method may further comprise outputting the predicted process parameter and/or the result of the comparison of the actual process parameter with the predicted process parameter via at least one output interface or port. The output may include a set of predicted process parameters and/or a set of comparisons of actual process parameters to predicted process parameters. As used herein, the term "output" is a broad term and is given its ordinary and customary meaning to those skilled in the art and is not limited to a specific or customized meaning. The term may particularly refer to, but is not limited to, a process of providing information to another system, data storage, individual or entity. As one embodiment, the output may be via one or more interfaces, such as a computer interface or a human interface. As one embodiment, the output may be in one or more of a computer readable format, a visual format, or an audible format. For example, the output may be via at least one display, at least one microphone, or the like.

Method steps a) to d) may be repeated, wherein an adapted simulation model may be used in step a).

In a further aspect of the invention, a computer program comprises instructions which, when executed by a computer or computer system, cause the computer or computer system to perform the method according to the invention, in particular steps a) to d). For possible definitions of most terms used herein, reference is made to the description of computer-implemented methods above, or as described in further detail below.

In particular, the computer program may be stored on a computer readable data carrier and/or a computer readable storage medium. As used herein, the terms "computer-readable data carrier" and "computer-readable storage medium" may particularly refer to non-transitory data storage devices, such as hardware storage media having computer-executable instructions stored thereon. The computer readable data carrier or storage medium may in particular be or comprise a storage medium such as a Random Access Memory (RAM) and/or a Read Only Memory (ROM).

Further disclosed and proposed herein is a computer program product comprising instructions which, when the program is executed by a computer or computer system, cause the computer or computer system to perform a computer-implemented method as described above or as described in further detail below. Thus, for possible definitions of most terms used herein, reference may again be made to the description of the method disclosed in the first aspect of the invention.

In particular, the computer program product may comprise program code means stored on a computer readable data carrier for performing a method according to one or more embodiments disclosed herein when the program is executed in a computer or a computer network. As used herein, a computer program product refers to a program that is a tradable product. The product may generally be present in any format, such as paper format, or on a computer readable data carrier. In particular, the computer program product may be distributed via a data network.

Further disclosed and proposed herein is a computer-readable storage medium comprising instructions that, when executed by a computer or computer system, cause the computer or computer system to perform a computer-implemented method as described above or as described in further detail below. Thus, for possible definitions of most terms used herein, reference may again be made to the description of the method disclosed in the first aspect of the invention.

In another aspect, an automated control system for an injection molding process in at least one injection molding machine is disclosed. The injection molding process is based on a number of process parameters.

The control system includes at least one external processing unit configured to simulate the injection molding process by applying an optimization algorithm of at least one optimization objective aspect on the simulation model based on an input parameter set including at least one simulation model, material specific parameters, and injection molding machine parameters.

The control system includes at least one interface configured to provide predicted process parameters to the injection molding machine. The control system is configured to perform at least one injection molding process using the injection molding machine to generate at least one workpiece based on the predicted process parameters. The control system is configured for determining at least one property of the generated workpiece, comparing the property to an optimization target, and adapting at least one process parameter of the injection molding machine based on the comparison. The control system is configured to repeat the injection molding process, determine the attributes, compare the attributes to the optimization targets, and adapt the process parameters until the attributes of the generated workpiece are consistent with the optimization targets, at least within a predetermined tolerance.

The control system is configured for determining at least one actual process parameter of the injection molding process. The control system is configured to compare the actual process parameter to the predicted process parameter and adapt the simulation model based on the comparison.

The automatic control system may be configured to perform the method according to the invention. Thus, for possible definitions of most terms used herein, reference may again be made to the description of the method disclosed in the first aspect of the invention.

The methods, systems and programs of the present invention have a number of advantages over methods, systems and programs known in the art. In particular, the methods, systems, and programs disclosed herein may improve the performance of injection molding processes as compared to devices, methods, and systems known in the art. The simulation may run on a cloud solution. The invention proposes that the simulation model is run in the cloud to determine the optimal parameters (to be processed) and that this information can be linked to the actual parameters (e.g. the actual parameters being processed) so that a fast and efficient evaluation cycle is run. By digital identity, the simulation model may also take into account material specific properties to further improve the simulation.

In view of the above, without excluding other possible embodiments, the following embodiments are conceivable:

embodiment 1 a computer-implemented method for controlling and/or monitoring at least one injection molding process in at least one injection molding machine, wherein the injection molding process is based on a plurality of process parameters, wherein the method comprises the steps of:

Embodiment 2 the method according to the preceding embodiment, wherein method steps a) to d) are repeated, wherein an adapted simulation model is used in step a).

Embodiment 3 the method of any of the preceding embodiments, wherein the injection molding machine parameters comprise at least one parameter selected from the group consisting of: polymer melt temperature, barrel temperature, injection unit temperature, screw speed, injection speed, holding pressure, holding time, cooling or solidification parameters.

Embodiment 4 the method according to any one of the preceding embodiments, wherein the measured parameters of the injection molding machine are registered and transmitted to the external processing unit, wherein the injection molding machine comprises at least one element selected from the group comprising: a temperature sensor; a pressure sensor; and (3) a clock.

Embodiment 5 the method of any of the preceding embodiments, wherein the simulation model comprises a fill simulation.

Embodiment 6 the method of any of the preceding embodiments, wherein the simulation model is configured to simulate filling a mold cavity with at least one molten mass of material.

Embodiment 7 the method of any of the preceding embodiments, wherein the simulation model is configured to simulate a geometry and/or shape of a workpiece.

Embodiment 8 the method of any of the preceding embodiments, wherein the simulation model comprises an intensity analysis.

Embodiment 9 the method of any of the preceding embodiments, wherein the material specific parameter comprises at least one parameter selected from the group consisting of: compressibility, flow characteristics, temperature characteristics.

Embodiment 10 the method of any of the preceding embodiments, wherein the simulation model is configured to consider material specific properties.

Embodiment 11 the method of any one of the preceding embodiments, wherein the simulation model is configured to consider batch properties of a batch of raw material.

Embodiment 12 the method of any of the preceding embodiments, wherein the property of the workpiece is at least one element selected from the group consisting of: the weight of the workpiece, the size of the workpiece, and the degree of warping.

Embodiment 13 the method of any of the preceding embodiments, wherein the optimization objective is at least one attribute of the workpiece.

Embodiment 14 the method of any of the preceding embodiments, wherein the method further comprises outputting the predicted process parameter and/or the comparison of the actual process parameter with the predicted process parameter via at least one output interface or port.

Embodiment 15 the method of any of the preceding embodiments, wherein the parameters of the simulation model are generated using at least one artificial neural network.

Embodiment 16 the method of any of the preceding embodiments, wherein the external processing unit is and/or comprises a cloud computing system.

Embodiment 17 a computer program comprising instructions which, when executed by a computer or computer system, cause the computer or computer system to perform the method according to any of the preceding embodiments.

Embodiment 18 a computer readable storage medium comprising instructions which, when executed by a computer or computer system, cause the execution of the method according to any of the preceding embodiments.

Embodiment 19 is an automated control system for an injection molding process in at least one injection molding machine, wherein the injection molding process is based on a plurality of process parameters, wherein the control system comprises at least one external processing unit, wherein the external processing unit is configured to simulate the injection molding process based on a set of input parameters comprising at least one simulation model, material specific parameters, and injection molding machine parameters, and configured to apply optimization parameters of at least one optimization objective aspect on the simulation model, wherein the control system comprises at least one interface configured to provide predicted process parameters to the injection molding machine, wherein the control system is configured to perform the at least one injection molding process using the injection molding machine based on the predicted process parameters, to generate at least one workpiece, wherein the control system is configured to determine at least one attribute of the generated workpiece, compare the attribute to the optimization objective, and adapt the at least one process parameter of the injection molding machine according to the comparison, wherein the control system is configured to repeat the injection molding process, determine the attribute, compare the attribute to the optimization objective, and adapt the process parameters within the predetermined process parameters to the actual process configuration, wherein the control system is configured to be matched to the actual process parameters based on the at least one of the predicted process parameters.

Embodiment 20 the automatic control system according to the preceding embodiment, wherein the automatic control system is configured for performing the method according to any of the preceding embodiments.

Drawings

Further optional features and embodiments will be disclosed in more detail in the following description of embodiments, preferably in connection with the dependent claims. Wherein the corresponding optional features may be implemented in a separate manner or in any arbitrary feasible combination, as will be appreciated by the skilled person. The scope of the invention is not limited by the preferred embodiments. Embodiments are schematically depicted in the drawings. Wherein like reference numbers refer to identical or functionally similar elements throughout the separate views.

In the drawings:

FIG. 1 illustrates one exemplary embodiment of a computer-implemented method and an automated control system for controlling and/or monitoring at least one injection molding process in at least one injection molding machine; and

fig. 2A to 2D show experimental results.

Detailed Description

Fig. 1 illustrates one exemplary embodiment of a computer-implemented method for controlling and/or monitoring at least one injection molding process in at least one injection molding machine 110 and an automated control system 112.

The injection molding machine 110 is configured to perform at least one injection molding process. The injection molding process may include at least one process or procedure to shape at least one material into any form or shape. The injection molding process may be a molding process performed by injecting a molten material into a mold. The mold may be a mold or a form, for example, a form giving a casting mold or a frame. In particular, as used herein, a mold may refer to any mold and/or molding that includes at least one cavity, such as at least one molding that gives a structure and/or cut. The mold may be particularly useful in an injection molding process wherein at least one block of molten material may be injected into at least one cavity of the mold. As one example, a mold having at least one cavity may be used in a molding process for forming a material. In particular, a mass of molten material injected into a mold cavity may be imparted to the negative form and/or geometry of the cavity. In particular, the mold may be used to fabricate at least one workpiece 114, wherein the fabricated workpiece may have a negative form and/or shape of the mold cavity.

The molding process may be configured for manufacturing at least one workpiece 114. The workpiece 114 may be any part or element. In particular, the workpiece 114 may be or may include components of any machine or device. For example, the workpiece 114 may have, at least in part, a negative shape (negative shape) of a mold or cavity of a mold in a molding process for manufacturing the part. Thus, the injection molding process may be or may refer to a shape imparting procedure for manufacturing the workpiece 114.

The injection molding process is based on a number of process parameters. The process parameters may be settable and/or selectable and/or adjustable and/or configurable parameters affecting the injection molding process. The process parameters may relate to the operating conditions of the injection molding machine 110. In particular, the process parameters may be injection molding machine parameters. For example, the process parameters may include one or more of polymer melt temperature, barrel temperature, injection unit temperature, screw speed, injection speed, holding pressure, holding time, cooling or solidification time, at least one cooling or solidification parameter (such as yield of cooling or solidification medium, or cooling or solidification medium temperature).

The method comprises the following steps:

a) Providing, by at least one external processing unit 118, a set of input parameters (denoted by reference numeral 116), wherein the set of input parameters includes at least one simulation model, material specific parameters, and injection molding machine parameters;

b) The external processing unit 118 simulates the injection molding process (indicated by reference numeral 120) based on the set of input parameters and determines at least one predicted process parameter 122 of the simulated injection molding process by applying an optimization algorithm on the simulation model with respect to at least one optimization objective, wherein the predicted process parameter is provided (indicated by reference numeral 124) to the injection molding machine 110 via at least one interface 126;

c) Performing (denoted by reference numeral 130) at least one injection molding process using the injection molding machine 110 based on the predicted process parameters to generate at least one workpiece 114, determining at least one attribute of the generated workpiece 114, and comparing the attribute to an optimization target (denoted by reference numeral 132), wherein in the event that the attribute of the generated workpiece 114 deviates from the optimization target, adapting at least one process parameter of the injection molding machine 110 according to the comparison, repeating the injection molding process with the adapted process parameters, determining the attribute of the generated workpiece 114, comparing the attribute to the optimization target until the attribute of the generated workpiece 114 coincides with the optimization target at least within a predetermined tolerance;

d) At least one actual process parameter of the injection molding process is determined (indicated by reference numeral 134), the actual process parameter and the predicted process parameter are compared, and a simulation model is adapted (indicated by reference numeral 136) based on the comparison.

The external processing unit 118 may be at least one processing unit designed separately from the injection molding machine 110. The injection molding machine 110 may include an internal processing unit, not shown herein, specifically configured for controlling and monitoring machine parameters. The external processing unit 118 may be configured to transmit data to and/or receive data from the internal processing unit via the at least one communication interface. The internal processing unit may be configured to transmit data to and/or receive data from the external processing unit via the at least one communication interface. The external processing unit 118 may comprise a plurality of processors. The external processing unit 118 may be and/or include a cloud computing system.

The external processing unit 118 may include at least one database. The database may be any collection of information. The database may be stored in at least one data storage device. The external processing unit 118 may comprise at least one data storage device in which information is stored. In particular, the database may contain any collection of information. The data storage device may be or may include at least one element selected from the group consisting of: at least one server, at least one server system comprising a plurality of servers, at least one cloud server, or a cloud computing infrastructure.

Providing 116 the input parameter set may include retrieving and/or selecting the input parameter set. Retrieval may include processing by a system (particularly a computer system) to generate data from any data source (such as from a data store, from a network, or from a further computer or computer system) and/or to obtain data. In particular, the retrieval may be via at least one computer interface (such as via a port such as a serial or parallel port). The retrieval may comprise several sub-steps, such as a sub-step of obtaining one or more primary information items and generating secondary information by utilizing the primary information (such as by applying one or more algorithms to the primary information, e.g. by using a processor).

The input parameter set may include information about the simulation model, material specific parameters, and injection molding machine parameters. The injection molding machine parameters may be parameters that affect the operating conditions of the injection molding machine. The injection molding machine parameters may include settings of machine components of the injection molding machine 110. The injection molding machine parameters may include specific values and/or parameter curves. The injection molding machine parameters may include at least one parameter selected from the group consisting of: polymer melt temperature, barrel temperature, injection unit temperature, screw speed, injection speed, holding pressure, holding time, cooling or solidification parameters (such as yield of cooling or solidification medium, cooling or solidification medium temperature). The injection molding machine parameters may further include the dimensions of the machine, such as mold clamping force, draw bar clearance, injection unit, the dimensions of the equipment of the machine, such as barrel diameter or maximum barrel temperature, etc.

The material specific parameter may be information about one or more materials used in the injection molding process. The material specific parameters may be provided by a material provider and/or may be downloaded from a website or other database. The material supplier may have a number of product specific data, such as rheology data, viscosity, and lot specific data for each material produced. The material specific parameters comprise at least one parameter selected from the group consisting of: compressibility, flow characteristics, temperature characteristics. The material (in particular the material used in the moulding process, for example for manufacturing the workpiece) may for example be or may comprise a plastics material. In particular, the plastic material may be or may comprise a thermoplastic material. Additionally or alternatively, the plastic material may be or include a thermoset material. Additionally or alternatively, the plastic material may comprise an elastic material. The material may be in a molten state specifically during fabrication of the workpiece 114.

The simulation model may be generated by software on the external processing unit 118 or the simulation model may be a dataset in the software. The simulation model may include at least one trained and trainable model. The external processing unit 118 may be configured to perform and/or execute at least one machine learning algorithm. The simulation model may be based on the results of at least one machine learning algorithm. The machine learning algorithm may include decision trees, naive bayes classification, nearest neighbor, neural network, convolutional neural network, generating an countermeasure network, support vector machine, linear regression, logistic regression, random forest, and/or gradient boosting algorithm. Preferably, the machine learning algorithm is organized to process inputs with high dimensions into outputs of much lower dimensions. The algorithm may be trained using a record of training data. The simulation model may include at least one algorithm and model parameters. The simulation model parameters may be generated using at least one artificial neural network. The simulation model, in particular the model parameters, may be adapted in step d) so that it may be further trained.

The simulation model may be configured to consider material specific properties. The simulation model may include digital twinning of the material. The simulation model may be configured to consider batch properties of a raw material batch, such as viscosity of the material batch.

It is possible to use simulation data, process data and product related data in process optimization of a cloud-based injection molding process. As mentioned above, the material provider may have a number of product specific data, such as rheological data, viscosity, and lot specific data for each material produced. The present invention proposes to establish a closed loop between the simulation and the injection molding process so that the simulation parameters can be used directly in the injection molding process. Furthermore, conversely, the process data can be used to optimize the modeling process using a machine learning model. By using cloud-based material and digital twinning of the injection molding process, lot specific information of the material can be further linked to simulation of the manufacturing process, resulting in a further increase in efficiency of the injection molding process.

The predicted process parameters 122 of the simulated injection molding process may be expected values of the process parameters, particularly for optimal manufacturing results and/or optimal use of resources.

Step b) may comprise at least one optimization step. Optimization may be the process of selecting the best parameter set from a parameter space of possible parameters, which is related to the optimization objective. The optimization objective may be at least one criterion under which the optimization is performed. The optimization objective may include at least one optimization objective and accuracy and/or precision. The optimization objective may be at least one attribute of the workpiece 114. The property of the workpiece 114 may be at least one element selected from the group consisting of: the weight of the workpiece 114, the size of the workpiece 114, and the degree of warpage. The optimization objective may be pre-specified, such as by at least one customer and/or a user of the at least one injection molding machine 110. The optimization objective may be a specification of at least one user. The user may choose to optimize the objective and the desired accuracy and/or precision. The predicted process parameters are provided to the injection molding machine 110 via at least one interface, in particular via a communication interface.

In step c), the manufactured workpiece 114 may be measured, for example, by using optical or tactile measurement techniques (such as scanning). Scanning may include determining the shape and size of the workpiece 114. The scanning may be performed specifically automatically. The scanning may be performed autonomously by the computer or by a network of computers.

The determined attributes of the workpiece 114 may be compared to optimization objectives. The comparison may include determining a deviation from the target shape and/or target size. If the difference between the determined attribute and the optimization target is above the tolerance limit, the generated workpiece 114 is considered to deviate from the target shape and/or target size. The tolerance limit may depend on such things as the accuracy of the determination of the attributes and/or the customer requirements.

If the generated properties of the workpiece 114 deviate from the optimization objectives, at least one process parameter of the injection molding machine 110 is adapted based on the comparison. The injection molding process repeatedly determines the properties of the generated workpiece 114 with the adapted process parameters and compares the properties with the optimization targets until the properties of the generated workpiece 114 agree with the optimization targets at least within a predetermined tolerance.

Step d) 134 includes determining at least one actual process parameter of the injection molding process. Injection molding machine 110 may be configured to measure and/or monitor at least one process parameter of the process during the injection molding process. The injection molding machine 110 may be configured to measure process parameters in real-time and adapt the process parameters during operation. The injection molding machine 110 may include at least one sensor. The measured parameters of the injection molding machine 110 may be registered and transmitted to an external processing unit. The injection molding machine 110 may include at least one element selected from the group consisting of: a temperature sensor; a pressure sensor; and (3) a clock.

Step d) 134 further includes comparing the actual process parameters to the predicted process parameters and adapting the simulation model based on the comparison. The comparison may include determining a deviation of the predicted process parameter from the actual process parameter, or vice versa. If the difference is above the tolerance limit, the actual process parameter is deemed to deviate from the predicted process parameter. The tolerance limit may depend on the measurement accuracy. The comparison may be performed by an internal processing unit of the injection molding machine. Information about the deviations and/or the actual process parameters may be transmitted to an external processing unit. The external processing unit may be configured to adapt the simulation model, in particular the model parameters, based on information about the deviations and/or the actual process parameters.

The method may further comprise outputting the predicted process parameter and/or the result of the comparison of the actual process parameter with the predicted process parameter via at least one output interface or port. Output may include the process of providing information to another system, data storage, individual, or entity. As one embodiment, the output may be via one or more interfaces, such as a computer interface or a human interface. As one embodiment, the output may be in one or more of a computer readable format, a visual format, or an audible format.

Further, an automatic control system 112 is shown in fig. 1. The injection molding process is based on a number of process parameters. The control system 112 includes at least one external processing unit 118. The external processing unit 118 is configured to simulate the injection molding process by applying an optimization algorithm in terms of at least one optimization objective on the simulation model based on an input parameter set comprising at least one simulation model, material specific parameters and injection molding machine parameters. The control system 112 includes at least one interface, indicated by arrow 138, configured to provide predicted process parameters to the injection molding machine 110. The control system 112 is configured to perform at least one injection molding process using the injection molding machine 110 to generate at least one workpiece 114 based on the predicted process parameters. The control system 112 is configured to determine at least one attribute of the generated workpiece 114, compare the attribute to an optimization objective, and adapt at least one process parameter of the injection molding machine 110 based on the comparison. The control system 112 is configured to repeat the injection molding process, determine the attributes, compare the attributes to the optimization targets, and adapt the process parameters until the attributes of the generated workpiece are consistent with the optimization targets, at least within predetermined tolerances. The control system 112 is configured for determining at least one actual process parameter of the injection molding process. The control system 112 is configured to compare the actual process parameters to the predicted process parameters and adapt the simulation model based on the comparison.

The automatic control system 112 may be configured to perform the method according to the present invention. Thus, for possible embodiments, reference may be made to the description of the method.

For example, comparing the determined properties of the workpiece 114 with the optimization objectives may reveal that the workpiece 114 deviates from the desired shape, particularly that warpage such as twisting, warping, wavy surfaces, and angular deviations occur. This may be due to the different shrinkage tendencies (shrinkage potential) of the various regions of the workpiece 114. The difference in shrinkage may be due to the different degree of accumulation in different regions of the workpiece 114, as well as the different orientation of the fibers and polymer chains. A further reason may be that the selected mold temperature is disadvantageous, the molded work piece 114 has a different wall thickness, the pressure gradient of the work piece 114 is too high along the flow path, the selected cooling time is too short such that the work piece 114 is removed from the mold at too high a temperature and the work piece 114 is deformed after removal from the mold, an disadvantageous material is used, or the glass fiber reinforced thermoplastic glass fibers are oriented mainly in the flow direction. In the latter case, deviations may occur if the orientation of the glass fibers varies at different places. This is due to, for example, an offset in the flow, an orientation effect at the flow path ends, weld lines and gates. Based on the comparison, at least one of the following process parameters of the injection molding machine 110 may be adapted: changing the temperature of the mold halves and sliding cores, increasing cooling time, adapting the process so that the mold is not stitched or negative drawn Hold, change hold pressure, and change hold time. Furthermore, the materials used may be changed in consideration of the comparison. In particular materials with low warp curvature, such as mixtures with amorphous phases, can be used. In addition, the workpiece design may also be changed. The process parameters of the injection molding machine may be adapted with respect to a predetermined hierarchy. For example, the mold temperature may be adapted first, and then the cooling time may be adapted. Subsequently, further process parameters may be adapted. FIGS. 2A-2C show die temperature versus temperature

The effect of warping of the finished clamping mandrel. For fig. 2A-2C, the mold temperature of the cavity is 80 ℃. The mold temperature of the core of fig. 2A is 80 ℃, fig. 2B is 30 ℃, and fig. 2C is 50 ℃. The gaps between the elements holding the mandrel are different in the figures. In fig. 2A, the gap is 1.0mm, fig. 2B is 5.0mm, and fig. 2C is 2.4mm. FIG. 2D shows another glass fiber reinforced +.>

Examples of the insulating plate made. The upper part of fig. 2D shows the geometry of the molded part optimized by simulation, the lower part shows the original case.

Reference marks

110. Injection molding machine

112. Automatic control system

114. Workpiece

116. Providing input parameter sets

118. External processing unit

120. Simulation of

122. Predicted process parameters for a simulated injection molding process

124. Providing predicted process parameters

126. Interface

130. Execution of

132. Comparison of

134. Determining at least one actual process parameter

136. Adaptation of

138. Interface

Claims

1. A computer-implemented method for controlling and/or monitoring at least one injection molding process in at least one injection molding machine (110), wherein the injection molding process is based on a plurality of process parameters, wherein the method comprises the steps of:

a) Providing, by at least one external processing unit (118), a set of input parameters, wherein the set of input parameters comprises at least one simulation model, material specific parameters and injection molding machine parameters;

b) An external processing unit (118) simulating the injection molding process based on the set of input parameters and determining at least one predicted process parameter of the simulated injection molding process by applying an optimization algorithm of at least one optimization objective aspect on the simulation model, wherein the predicted process parameter is provided to the injection molding machine via the at least one interface;

c) Performing at least one injection molding process using the injection molding machine (110) to generate at least one workpiece (114) based on the predicted process parameters, determining at least one attribute of the generated workpiece (114), and comparing the attribute to an optimization target, wherein in case the attribute of the generated workpiece (114) deviates from the optimization target, adapting at least one process parameter of the injection molding machine (110) according to the comparison, repeating the injection molding process with the adapted process parameters, determining the attribute of the generated workpiece (114), and comparing the attribute to the optimization target until the attribute of the generated workpiece (114) coincides with the optimization target at least within a predetermined tolerance;

2. Method according to the preceding claim, wherein method steps a) to d) are repeated, wherein in step a) an adapted simulation model is used.

3. The method of any of the preceding claims, wherein the injection molding machine parameters comprise at least one parameter selected from the group consisting of: polymer melt temperature, barrel temperature, injection unit temperature, screw speed, injection speed, holding pressure, holding time, cooling or solidification parameters.

4. The method according to any of the preceding claims, wherein measured parameters of the injection molding machine (110) are registered and transmitted to an external processing unit (118), wherein the injection molding machine (110) comprises at least one element selected from the group comprising: a temperature sensor; a pressure sensor; and (3) a clock.

5. A method according to any of the preceding claims, wherein the simulation model comprises a filling simulation.

6. The method according to any one of the preceding claims, wherein the simulation model is configured to simulate filling a mold cavity with at least one molten mass of material.

7. A method according to any one of the preceding claims, wherein the simulation model is configured to simulate the geometry and/or shape of a workpiece.

8. The method of any of the preceding claims, wherein the simulation model comprises an intensity analysis.

9. The method of any one of the preceding claims, wherein the material specific parameter comprises at least one parameter selected from the group consisting of: compressibility, flow characteristics, temperature characteristics.

10. The method of any of the preceding claims, wherein the simulation model is configured to take into account material specific properties.

11. The method of any one of the preceding claims, wherein the simulation model is configured to consider batch properties of a batch of raw material.

12. The method according to any of the preceding claims, wherein the method further comprises outputting the predicted process parameter and/or the result of the comparison of the actual process parameter with the predicted process parameter via at least one output interface or port.

13. The method according to any of the preceding claims, wherein the external processing unit (118) is and/or comprises a cloud computing system.

14. A computer program comprising instructions which, when executed by a computer or computer system, cause the computer or computer system to perform the method of any preceding claim.

15. An automatic control system (112) for an injection molding process in at least one injection molding machine (110), wherein the injection molding process is based on a plurality of process parameters, wherein the control system (112) comprises at least one external processing unit (118), wherein the external processing unit (118) is configured to simulate the injection molding process based on an input parameter set comprising at least one simulation model, material specific parameters and injection molding machine parameters, and configured to apply optimization parameters of at least one optimization objective aspect on the simulation model, wherein the control system (112) comprises at least one interface, the at least one interface (138) is configured to provide the injection molding machine (110) with predicted process parameters, wherein the control system (112) is configured to perform the at least one injection molding process using the injection molding machine (110) based on the predicted process parameters to generate at least one workpiece (114), wherein the control system (112) is configured to determine at least one property of the generated workpiece (114), compare the property to the optimization objective, and adapt the at least one control system (138) to the optimization objective in accordance with the comparison process parameters until the at least one property of the injection molding machine (110) is configured to match the process property to the optimization objective, wherein the control system (112) is configured for determining at least one actual process parameter of the injection molding process, wherein the control system (112) is configured for comparing the actual process parameter with the predicted process parameter and adapting the simulation model based on the comparison.